Ask Your Question
0

Is it possible to use GPU for forward pass of a tensorflow model in opencv 3.4.1 dnn

asked 2018-05-17 04:24:47 -0500

AyushP123 gravatar image

Was trying to find a GPU implementation of dnn::forward .... wanted to know if there is any work being done?? .... and would the workaround this would be to get all the weights and write a cuda version of forward pass myself??

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
0

answered 2018-05-17 04:26:50 -0500

berak gravatar image

updated 2018-05-17 04:28:05 -0500

if you have a decent GPU, you can try the opencl target, but there is no support for cuda at all here.

and would the workaround this would be to get all the weights and write a cuda version of forward pass myself??

good luck with that idea, it means rewriting the whole dnn module on your own.

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

1 follower

Stats

Asked: 2018-05-17 04:24:47 -0500

Seen: 28 times

Last updated: May 17